Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    accustomed to or used to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sexes
    1.32
    "></
    1.16
     conseils
    1.12
    一共
    1.12
    "]
    1.09
    ];
    1.07
    नीचर
    1.07
    ">=</
    1.03
    </strong>
    1.02
     earnest
    1.01
    POSITIVE LOGITS
    ب
    1.40
    るので
    1.39
    izes
    1.38
    ade
    1.33
    ﻡ
    1.32
     viven
    1.31
    なあ
    1.30
    2
    1.30
    ُر
    1.30
    ık
    1.29
    Act Density 0.022%

    No Known Activations